Fewshot_Detection icon indicating copy to clipboard operation
Fewshot_Detection copied to clipboard

Published 20 hours ago • verified publisher icon bingykang

CUDA out of memory

Open ghost opened this issue 5 years ago • 6 comments

I have finished trained the model, but when I tried to evaluate the model, it printed out 'CUDA out of memory'. I have 2 GPUs and 32GB. But I can't use 2GPUs to evaluate. It evaluated with 1GPU every time even though I have changed gpu to "0,1" in valid_ensemble.py. Do you have any suggestion or solution?

ghost avatar Dec 09 '19 14:12 ghost

hello,I get this question, too. Have you solve this problem?

CHS18895660306 avatar Sep 19 '20 11:09 CHS18895660306

Do you solve the problem?

lander1003 avatar Apr 07 '21 00:04 lander1003

you should reduce batchsize.

aeinsara avatar Jul 31 '21 10:07 aeinsara

@aeinsara Hi! I have tried to decrease the batch size, but It is not working. Have you solved this problem?

MartinYYYYan avatar Sep 15 '21 06:09 MartinYYYYan

  1. reduce batchsize
  2. update your graphic card(lol)
  3. disable random
  4. increase subdivisions

MusherM avatar Apr 21 '22 07:04 MusherM

hello,I met this same question, too. Have you solved this problem?

GDDKRJ avatar Jan 06 '23 02:01 GDDKRJ